Investigating the Robustness of Deductive Reasoning with Large Language Models

2025-02-04

AI Summary

This study systematically evaluates the robustness of large language models (LLMs) in deductive reasoning, focusing on vulnerabilities in informal-text formalization and inference processes. Method: We propose the first dedicated evaluation framework for LLM-based deductive reasoning robustness, constructing a perturbation dataset comprising seven categories of adversarial noise and counterfactual statements; we decouple impacts along three dimensions—formalization syntax, inference format, and error-recovery feedback. Contribution/Results: Counterfactual perturbations universally degrade performance across all methods, whereas adversarial noise primarily impairs automatic formalization. Detailed feedback mitigates syntactic errors but fails to improve overall reasoning accuracy. These findings expose critical bottlenecks in current LLM-based deductive reasoning—particularly in handling counterfactuals and recovering from formalization failures—and provide empirical grounding and methodological guidance for developing robust, trustworthy reasoning systems.

Technology Category

• Natural Language Processing: Safety and Robustness
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large Language Models (LLMs) have been shown to achieve impressive results for many reasoning-based Natural Language Processing (NLP) tasks, suggesting a degree of deductive reasoning capability. However, it remains unclear to which extent LLMs, in both informal and autoformalisation methods, are robust on logical deduction tasks. Moreover, while many LLM-based deduction methods have been proposed, there is a lack of a systematic study that analyses the impact of their design components. Addressing these two challenges, we propose the first study of the robustness of LLM-based deductive reasoning methods. We devise a framework with two families of perturbations: adversarial noise and counterfactual statements, which jointly generate seven perturbed datasets. We organize the landscape of LLM reasoners according to their reasoning format, formalisation syntax, and feedback for error recovery. The results show that adversarial noise affects autoformalisation, while counterfactual statements influence all approaches. Detailed feedback does not improve overall accuracy despite reducing syntax errors, pointing to the challenge of LLM-based methods to self-correct effectively.

Problem

• Assess robustness of LLMs in deductive reasoning
• Analyze impact of design components in LLM methods
• Evaluate effectiveness of feedback for error correction

Innovation

• LLM-based deductive reasoning robustness
• Adversarial noise and counterfactual perturbations
• Systematic study of LLM design components